Wednesday 20th of September 2017
 

A Novel Approach for Credit Card Fraud Detection Targeting the Indian Market


Jaba Suman Mishra, Soumyashree Panda and Ashis Kumar Mishra

Due to a rapid advancement in the electronic commerce technology, the use of credit cards has dramatically increased. So, the rate of fraudulent practices is also increasing every year. In this paper we present the necessary theory to detect fraud in credit card transaction processing using a Hidden Markov Model. If an incoming credit card transaction is not accepted by the Hidden Markov Model with sufficiently high probability, it is considered to be fraudulent. At the same time, we try to ensure that genuine transactions are not rejected. We show how HMM helps to obtain high fraud coverage combined with a low false alarm rate. The existing models detect that a fraud has occurred only after the fraudulent transaction is completed but in our proposed model, we have shown how it can be reported instantly while the fraudulent transaction is on process.

Keywords: Electronic commerce, Credit card, Fraud detection system, Hidden Markov Model, False alarm.

Download Full-Text


ABOUT THE AUTHORS

Jaba Suman Mishra
Jaba Suman Mishra is currently pursuing bachelorís degree program (2009-2013) in computer science and engineering in College of Engineering and Technology (BPUT), Odisha, India. Her current Field of research being Machine Learning and Data Mining.

Soumyashree Panda
Soumyashree Panda is currently pursuing bachelorís degree program (2009-2013) in computer science and engineering in College of Engineering and Technology (BPUT), Odisha, India. Her current Field of research being Machine Learning and Data Mining.

Ashis Kumar Mishra
Ashis Kumar Mishra has completed his post graduate from KIIT University(2011) and under graduate from Biju Pattnaik University of Technology (2007). He is currently a faculty member in Department of Computer Science and Engineering in College of Engineering and Technology, Bhubaneswar, Odisha, India. He has published 10 numbers of International Journals and a National Conference in fields of Cryptography, Real Time Systems, Evolutionary algorithm, Cloud Computing and Machine learning.


IJCSI Published Papers Indexed By:

 

 

 

 
About IJCSI

IJCSI is a refereed open access international journal for scientific papers dealing in all areas of computer science research...

Learn more »
Join Us
FAQs

Read the most frequently asked questions about IJCSI.

Frequently Asked Questions (FAQs) »
Get in touch

Phone: +230 911 5482
Email: info@ijcsi.org

More contact details »